# What is the status of pretrained standard models (for machine learning) in the Julia ecosystem?
**URL:** https://discourse.julialang.org/t/what-is-the-status-of-pretrained-standard-models-for-machine-learning-in-the-julia-ecosystem/97702
**Category:** Machine Learning
**Created:** [April 20, 2023, 12:38pm UTC](https://discourse.julialang.org/t/what-is-the-status-of-pretrained-standard-models-for-machine-learning-in-the-julia-ecosystem/97702 "2023-04-20T12:38:21Z")
**Posts on this page:** 6
**Page:** 1
### Author:  [@Euhan](https://discourse.julialang.org/u/Euhan)
#### Post date: [April 20, 2023, 12:38pm UTC](https://discourse.julialang.org/t/what-is-the-status-of-pretrained-standard-models-for-machine-learning-in-the-julia-ecosystem/97702/1 "2023-04-20T12:38:22Z")
I have previously tried using Metalhead to take advantage of standard nets, but I haven’t been able to use anything with pretrained weights. Or rather, at the time none of the models I looked at, had weights.
What is the status of pretrained models at the moment? Can you get models with weights through Metalhead now? Is there another better way to accomplish something similar.
---
### Author:  [@gdalle](https://discourse.julialang.org/u/gdalle)
#### Post date: [April 20, 2023, 3:45pm UTC](https://discourse.julialang.org/t/what-is-the-status-of-pretrained-standard-models-for-machine-learning-in-the-julia-ecosystem/97702/2 "2023-04-20T15:45:44Z")
I think Boltz has those? ping @avikpal
> **[GitHub - LuxDL/Boltz.jl: Accelerate your ML research using pre-built Deep...](https://github.com/LuxDL/Boltz.jl)**
>
> Accelerate your ML research using pre-built Deep Learning Models with Lux - GitHub - LuxDL/Boltz.jl: Accelerate your ML research using pre-built Deep Learning Models with Lux
---
### Author:  [@ToucheSir](https://discourse.julialang.org/u/ToucheSir)
#### Post date: [April 20, 2023, 3:53pm UTC](https://discourse.julialang.org/t/what-is-the-status-of-pretrained-standard-models-for-machine-learning-in-the-julia-ecosystem/97702/3 "2023-04-20T15:53:16Z")
Which models did you look at, specifically and when?
---
### Author:  [@Euhan](https://discourse.julialang.org/u/Euhan)
#### Post date: [April 21, 2023, 9:52am UTC](https://discourse.julialang.org/t/what-is-the-status-of-pretrained-standard-models-for-machine-learning-in-the-julia-ecosystem/97702/4 "2023-04-21T09:52:37Z")
I’m sorry, I haven’t documented this. It seems it might have been one year ago or a bit more. Models might have included VGG but I can’t remember.
How so? Did Metalhead provide weights for all or most of its models recently?
---
### Author:  [@ToucheSir](https://discourse.julialang.org/u/ToucheSir)
#### Post date: [April 22, 2023, 8:45pm UTC](https://discourse.julialang.org/t/what-is-the-status-of-pretrained-standard-models-for-machine-learning-in-the-julia-ecosystem/97702/5 "2023-04-22T20:45:15Z")
If by recently you count almost a year ago, then yes: [Add pre-trained models from HuggingFace and add accuracy testing by darsnack · Pull Request #164 · FluxML/Metalhead.jl · GitHub](https://github.com/FluxML/Metalhead.jl/pull/164)
---
### Author:  [@Euhan](https://discourse.julialang.org/u/Euhan)
#### Post date: [April 24, 2023, 6:23pm UTC](https://discourse.julialang.org/t/what-is-the-status-of-pretrained-standard-models-for-machine-learning-in-the-julia-ecosystem/97702/6 "2023-04-24T18:23:20Z")
Sounds good. I’ll see if I can use it.